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. 9052
    Prev
    Next
    INDEX
    Explanations

    large numbers and zeros

    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
    ibini
    -0.08
    /apps
    -0.08
    .compat
    -0.07
    iosamente
    -0.07
     angenehm
    -0.07
     conflict
    -0.07
    illera
    -0.07
    	can
    -0.07
    ientemente
    -0.07
     dietary
    -0.07
    POSITIVE LOGITS
     trillion
    0.10
     suppression
    0.08
     Billion
    0.08
    Zeros
    0.08
     zeros
    0.08
     spelled
    0.08
    Null
    0.07
    Counting
    0.07
     bells
    0.07
     dite
    0.07
    Activations Density 0.016%

    No Known Activations