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. 44016
    Prev
    Next
    INDEX
    Explanations

    space

    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
     blant
    -0.08
     rück
    -0.08
     Mina
    -0.08
     voces
    -0.08
    甲
    -0.08
    outines
    -0.08
    Voice
    -0.08
     ambientais
    -0.08
     voices
    -0.08
     máxima
    -0.07
    POSITIVE LOGITS
     peril
    0.08
    cu
    0.08
    Пр
    0.08
    (h
    0.08
    .Align
    0.07
    (str
    0.07
    sie
    0.07
    +h
    0.07
    =str
    0.07
    APE
    0.07
    Activations Density 0.001%

    No Known Activations