© 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. 102855
    Prev
    Next
    INDEX
    Explanations

    There

    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
     Среди
    -0.09
     ترسره
    -0.09
     uitstr
    -0.09
     löyty
    -0.09
     табылады
    -0.09
     које
    -0.09
    ेदार
    -0.08
    _TC
    -0.08
     בעוד
    -0.08
    /XML
    -0.08
    POSITIVE LOGITS
     can
    0.12
     will
    0.12
     may
    0.12
    udover
    0.11
     could
    0.11
    by
    0.11
     might
    0.10
     wouldn't
    0.10
     Different
    0.09
     diferentes
    0.09
    Activations Density 0.033%

    No Known Activations