Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130964
    Prev
    Next
    INDEX
    Explanations

    dash/angle brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Holmes
    -0.08
     техники
    -0.08
     TLC
    -0.08
    Gang
    -0.07
    gang
    -0.07
     сл
    -0.07
    �
    -0.07
     Hernández
    -0.07
    �
    -0.07
    annte
    -0.07
    POSITIVE LOGITS
    _EMPTY
    0.08
    ARGS
    0.08
     arguments
    0.08
    Mensagem
    0.08
    есс
    0.07
    Throttle
    0.07
     بنی
    0.07
    Empty
    0.07
    empty
    0.07
     consumed
    0.07
    Activations Density 0.005%

    No Known Activations