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. 76399
    Prev
    Next
    INDEX
    Explanations

    Broadly about general topics

    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
    ..."↵↵
    -0.08
     relentless
    -0.08
     към
    -0.08
    avio
    -0.08
    erca
    -0.08
     leto
    -0.07
     curiosity
    -0.07
     acero
    -0.07
     gif
    -0.07
     thousands
    -0.07
    POSITIVE LOGITS
    Vector
    0.10
    Bundles
    0.09
    _vect
    0.09
    Propagation
    0.08
    _Vector
    0.08
     éta
    0.08
    <Vector
    0.08
    Subset
    0.08
     communic
    0.08
     nuanced
    0.08
    Activations Density 0.000%

    No Known Activations