© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50840
    Prev
    Next
    INDEX
    Explanations

    Video surveillance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chemotherapy
    -0.11
     Calculator
    -0.10
     gyóg
    -0.10
     книга
    -0.09
     Kaffee
    -0.09
     guitarra
    -0.09
    Calculator
    -0.09
     perfume
    -0.09
     guitars
    -0.09
     الكيمي
    -0.08
    POSITIVE LOGITS
    录像
    0.18
     surveillance
    0.16
     DVR
    0.15
    高清视频
    0.15
     vigilancia
    0.15
     footage
    0.14
     高清
    0.14
     Surveillance
    0.14
    高清
    0.14
     livestream
    0.14
    Activations Density 0.031%

    No Known Activations