© 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. 50674
    Prev
    Next
    INDEX
    Explanations

    Geometry with triangles

    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
    inas
    -0.08
    atos
    -0.08
    न
    -0.08
    нях
    -0.08
    Vod
    -0.08
    enen
    -0.07
    odas
    -0.07
     साह
    -0.07
    bold
    -0.07
    náv
    -0.07
    POSITIVE LOGITS
     lond
    0.08
     provincia
    0.08
    oi
    0.08
    ifa
    0.07
    oire
    0.07
     ultras
    0.07
     Gér
    0.07
     einger
    0.07
     prét
    0.07
    રી
    0.07
    Activations Density 0.004%

    No Known Activations