© 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. 19-RESID-POST-AA
    11. 102617
    Prev
    Next
    INDEX
    Explanations

    can

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _Create
    -0.08
     inclus
    -0.08
    _possible
    -0.08
    가능
    -0.08
     repetitions
    -0.08
     האפשר
    -0.08
    _Write
    -0.08
    Confira
    -0.07
     inclusión
    -0.07
    -repeat
    -0.07
    POSITIVE LOGITS
     concurrently
    0.10
     concurrent
    0.09
     одновременно
    0.09
     अर्को
    0.09
     expired
    0.09
     simultaneous
    0.08
     동시에
    0.08
    expired
    0.08
     gleichzeitig
    0.08
    0.08
    Activations Density 0.006%

    No Known Activations