Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52876
    Prev
    Next
    INDEX
    Explanations

    VR and Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snd
    -0.09
     PNG
    -0.08
     png
    -0.08
     Hacienda
    -0.08
     Fior
    -0.08
     szybko
    -0.08
     jordan
    -0.07
     PDE
    -0.07
     breeder
    -0.07
    _strip
    -0.07
    POSITIVE LOGITS
     fauteuil
    0.08
    yleft
    0.08
     हथ
    0.08
    ithand
    0.08
     ray
    0.08
     weapon
    0.08
    Touchable
    0.08
    ु�
    0.08
     glove
    0.08
    obutton
    0.07
    Activations Density 0.003%

    No Known Activations