© 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. 49155
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    D
    -0.08
    [D
    -0.08
    >D
    -0.08
    �
    -0.08
     хозяй
    -0.08
    +D
    -0.08
     deput
    -0.08
    Christine
    -0.07
    BUM
    -0.07
    Ges
    -0.07
    POSITIVE LOGITS
    প্র
    0.07
    m
    0.07
    aff
    0.07
    illen
    0.07
    atlar
    0.07
     throm
    0.07
     notebook
    0.07
    Checked
    0.07
     lymph
    0.07
     M
    0.07
    Activations Density 0.009%

    No Known Activations