© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48070
    Prev
    Next
    INDEX
    Explanations

    values

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nth
    -0.08
    acle
    -0.08
    entity
    -0.08
    actor
    -0.08
    acles
    -0.08
    image
    -0.08
    prime
    -0.08
    item
    -0.07
     synonym
    -0.07
    plugins
    -0.07
    POSITIVE LOGITS
     values
    0.25
     xs
    0.20
     valores
    0.20
    _values
    0.20
     waarden
    0.20
     Values
    0.20
     Werte
    0.19
    values
    0.19
     valeurs
    0.19
    Values
    0.19
    Activations Density 0.129%

    No Known Activations