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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98654
    Prev
    Next
    INDEX
    Explanations

    VBA worksheet events

    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
    પી
    -0.09
    ansi
    -0.08
     APPLICATION
    -0.08
    _handler
    -0.08
    _HANDLER
    -0.07
     salida
    -0.07
    ైల
    -0.07
    uab
    -0.07
    хід
    -0.07
    async
    -0.07
    POSITIVE LOGITS
     competencia
    0.08
     commod
    0.07
    nok
    0.07
     regarde
    0.07
    Zoom
    0.07
    �
    0.07
     invests
    0.07
     نما
    0.07
     fixture
    0.07
    rame
    0.07
    Activations Density 0.001%

    No Known Activations