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. 15-RESID-POST-AA
    6. 19575
    Prev
    Next
    INDEX
    Explanations

    by and colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Always
    -0.08
    nerg
    -0.08
    PIRED
    -0.08
    ENGE
    -0.08
     dadas
    -0.08
     GIVEN
    -0.08
    $field
    -0.07
    Include
    -0.07
    нь
    -0.07
    $args
    -0.07
    POSITIVE LOGITS
     restraints
    0.09
    ović
    0.08
     divisible
    0.08
    _div
    0.08
    _marshaled
    0.08
    _thumbnail
    0.08
     dividing
    0.08
    _pipeline
    0.08
     Stir
    0.08
     хэрэг
    0.08
    Activations Density 0.014%

    No Known Activations