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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97767
    Prev
    Next
    INDEX
    Explanations

    place

    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
    Series
    -0.08
     series
    -0.08
     כול
    -0.07
    -0.07
    series
    -0.07
     boven
    -0.07
     escenarios
    -0.07
     құрам
    -0.07
    Scenario
    -0.07
     série
    -0.07
    POSITIVE LOGITS
    处
    0.47
    處
    0.34
    处分
    0.32
    地方
    0.26
     miejscu
    0.22
    位置
    0.22
     സ്ഥല
    0.21
     സ്ഥാന
    0.20
     месте
    0.20
     처
    0.20
    Activations Density 0.041%
    No Known Activations