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. 119311
    Prev
    Next
    INDEX
    Explanations

    uses

    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
     indis
    -0.08
    itary
    -0.07
     circumvent
    -0.07
     overcoming
    -0.07
    ொட
    -0.07
    opathy
    -0.07
    Or
    -0.07
     suy
    -0.07
    _max
    -0.07
    `.↵
    -0.06
    POSITIVE LOGITS
     قالب
    0.09
    컵
    0.09
    杯
    0.09
     предусматри
    0.09
     pants
    0.09
    लाइन
    0.09
     подраз
    0.09
     prévoit
    0.08
     ::=
    0.08
     Cup
    0.08
    Activations Density 0.009%

    No Known Activations