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. 24382
    Prev
    Next
    INDEX
    Explanations

    cheese

    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
     soon
    -0.08
    ES
    -0.07
     ingen
    -0.07
     médit
    -0.07
    'hui
    -0.07
    ోలు
    -0.07
    Top
    -0.07
    RSA
    -0.07
     MIT
    -0.07
     Sof
    -0.07
    POSITIVE LOGITS
     alley
    0.08
     Downs
    0.08
    atang
    0.08
     വിക
    0.08
    ーブル
    0.08
     deta
    0.08
     xlabel
    0.08
     Business
    0.08
    pedido
    0.07
     provocative
    0.07
    Activations Density 0.001%

    No Known Activations