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. 111581
    Prev
    Next
    INDEX
    Explanations

    convert

    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
    Warm
    -0.08
     warmth
    -0.08
    ████
    -0.08
     Warm
    -0.07
     �
    -0.07
    Mant
    -0.07
    aimana
    -0.07
    connector
    -0.07
    454
    -0.07
     Maz
    -0.07
    POSITIVE LOGITS
     Domino
    0.08
     abundant
    0.08
     sequence
    0.08
     grapes
    0.08
     abe
    0.08
     Sequence
    0.08
     stages
    0.07
    .sequence
    0.07
     Hobbit
    0.07
    .autocon
    0.07
    Activations Density 0.001%

    No Known Activations