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. 42232
    Prev
    Next
    INDEX
    Explanations

    Need

    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
     vert
    -0.07
    acle
    -0.07
     moi
    -0.07
     ook
    -0.07
     balade
    -0.07
    pur
    -0.07
    ツ
    -0.07
     vooral
    -0.07
    Sprint
    -0.07
    ่
    -0.07
    POSITIVE LOGITS
    ids
    0.08
    397
    0.08
     तथा
    0.08
    edt
    0.07
     emb
    0.07
    eys
    0.07
    emb
    0.07
    hecimento
    0.07
     Brust
    0.07
     સમગ્ર
    0.07
    Activations Density 0.184%

    No Known Activations