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. 90055
    Prev
    Next
    INDEX
    Explanations

    less

    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
    ential
    -0.09
    (clear
    -0.09
    entials
    -0.08
    enzial
    -0.08
    urations
    -0.08
    Wrapping
    -0.08
    _clear
    -0.08
    명
    -0.08
     rhythmic
    -0.08
    ancin
    -0.08
    POSITIVE LOGITS
     hemisphere
    0.08
    496
    0.08
     blk
    0.08
    465
    0.08
    288
    0.08
    uken
    0.07
    928
    0.07
    988
    0.07
     fyrir
    0.07
     déterminer
    0.07
    Activations Density 0.002%

    No Known Activations