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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75997
    Prev
    Next
    INDEX
    Explanations

    Packing lists

    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
    Encounter
    -0.08
     memor
    -0.08
     bares
    -0.08
     broadcasting
    -0.08
    Convention
    -0.08
     chord
    -0.07
     encountering
    -0.07
     lick
    -0.07
    _Rem
    -0.07
    \Session
    -0.07
    POSITIVE LOGITS
     орт
    0.09
    protected
    0.08
    ภ
    0.08
    gener
    0.08
     רב
    0.08
     consent
    0.08
    -ext
    0.08
    accent
    0.07
     הרב
    0.07
     Consent
    0.07
    Activations Density 0.007%

    No Known Activations