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. 102924
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     rallies
    -0.08
    ാൾ
    -0.08
     overcrow
    -0.08
     Reis
    -0.08
     demolished
    -0.08
     адамдар
    -0.08
     Mara
    -0.08
     ആള
    -0.07
     অতিথ
    -0.07
     venues
    -0.07
    POSITIVE LOGITS
    Pak
    0.09
    pak
    0.08
     vector
    0.08
     Pak
    0.08
    īga
    0.08
     vec
    0.08
     vetor
    0.08
    .Vector
    0.07
     rookie
    0.07
     nargs
    0.07
    Activations Density 0.045%

    No Known Activations