© 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. 11-RESID-POST-AA
    11. 47138
    Prev
    Next
    INDEX
    Explanations

    actions

    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
    �
    -0.09
    WC
    -0.08
    ßte
    -0.08
    ulek
    -0.08
    apte
    -0.08
    Destructor
    -0.08
     dong
    -0.07
     uiteraard
    -0.07
    itchie
    -0.07
    gehend
    -0.07
    POSITIVE LOGITS
    akaroon
    0.07
     reconstru
    0.07
    _FIRST
    0.07
     대
    0.07
     byg
    0.07
     groß
    0.07
    ля
    0.07
     foreigners
    0.07
     suele
    0.07
     Messiah
    0.07
    Activations Density 0.243%

    No Known Activations