© 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. 3-RESID-POST-AA
    11. 12972
    Prev
    Next
    INDEX
    Explanations

    IPS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horribly
    -0.08
     laden
    -0.08
    met
    -0.08
     uncl
    -0.07
    _PARAM
    -0.07
     hore
    -0.07
    ನ್ನು
    -0.07
     nase
    -0.07
    ,--
    -0.07
     conse
    -0.07
    POSITIVE LOGITS
     zwar
    0.08
     antif
    0.08
     와
    0.08
     V
    0.07
    kurs
    0.07
    licht
    0.07
    Cube
    0.07
    DDS
    0.07
     Helena
    0.07
     µ
    0.07
    Activations Density 0.000%

    No Known Activations