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. 46170
    Prev
    Next
    INDEX
    Explanations

    factor

    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
     cuch
    -0.08
     rappro
    -0.08
    poon
    -0.08
     gestalt
    -0.08
     desayuno
    -0.07
     또는
    -0.07
    /head
    -0.07
     or
    -0.07
    itek
    -0.07
     或
    -0.07
    POSITIVE LOGITS
     exponent
    0.11
    Exponent
    0.10
     expo
    0.09
     '?
    0.09
     ?.
    0.08
     '".$
    0.08
     expiration
    0.08
     perms
    0.08
     fibra
    0.08
     breakdown
    0.08
    Activations Density 0.030%

    No Known Activations