© 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. 7961
    Prev
    Next
    INDEX
    Explanations

    methylation

    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
    itchie
    -0.08
    itte
    -0.08
    repos
    -0.08
     whip
    -0.08
     Motors
    -0.08
    �
    -0.08
    _sessions
    -0.08
    animation
    -0.08
     refrigerators
    -0.07
     séances
    -0.07
    POSITIVE LOGITS
    ethyl
    0.10
     methyl
    0.10
     detectable
    0.09
     oxidation
    0.09
    โด
    0.08
     marking
    0.08
     billions
    0.08
     distinguishing
    0.08
    Cluster
    0.08
     synthetic
    0.08
    Activations Density 0.002%

    No Known Activations