© 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. 26534
    Prev
    Next
    INDEX
    Explanations

    Assembly code

    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
     renewable
    -0.08
     entraîne
    -0.08
    宗
    -0.08
    Renew
    -0.08
     democr
    -0.08
    ackle
    -0.08
    лаг
    -0.08
     garagem
    -0.08
     افضل
    -0.08
     agama
    -0.07
    POSITIVE LOGITS
    offsetof
    0.14
     offsetof
    0.13
    offset
    0.13
    -offset
    0.12
    OFFSET
    0.12
     OFFSET
    0.12
     offsets
    0.11
     offset
    0.11
    .Offset
    0.11
    _offset
    0.11
    Activations Density 0.004%

    No Known Activations