© 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. 144
    Prev
    Next
    INDEX
    Explanations

    Cryptocurrency and blockchain

    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
     �
    -0.10
     Covers
    -0.10
    MID
    -0.09
     волос
    -0.09
    covers
    -0.09
    Lil
    -0.08
     Сем
    -0.08
     behandeln
    -0.08
     behandelt
    -0.08
     내부
    -0.08
    POSITIVE LOGITS
     (
    0.09
    lela
    0.08
     arr
    0.08
     निष
    0.08
    ::↵↵
    0.08
     e
    0.07
     :=
    0.07
     disposizione
    0.07
    .Id
    0.07
    0.07
    Activations Density 0.001%

    No Known Activations