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. 59063
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     कट
    -0.09
    ,还
    -0.08
    Harvest
    -0.08
     Cutting
    -0.08
     Flow
    -0.08
     الهي
    -0.08
    gebnis
    -0.08
     Harvest
    -0.08
    (button
    -0.08
     анти
    -0.07
    POSITIVE LOGITS
     DDS
    0.09
     intermitt
    0.08
     ther
    0.08
    "%(
    0.07
     signatures
    0.07
     merely
    0.07
    ontos
    0.07
     avem
    0.07
    .Mult
    0.07
     plaintext
    0.07
    Activations Density 0.062%

    No Known Activations