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. 58693
    Prev
    Next
    INDEX
    Explanations

    racquet

    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
     Mode
    -0.08
     Leadership
    -0.07
    Remarks
    -0.07
     Buh
    -0.07
     Boc
    -0.07
    Regards
    -0.07
     Foundation
    -0.07
     Tc
    -0.07
     anchors
    -0.07
     Armen
    -0.07
    POSITIVE LOGITS
    ালে
    0.08
    _usuario
    0.08
     badminton
    0.08
    iast
    0.08
     vraag
    0.08
    यो
    0.07
    ಾಂತರ
    0.07
    usen
    0.07
     <$
    0.07
    usuario
    0.07
    Activations Density 0.004%

    No Known Activations