© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    ier

    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
    هاد
    -0.08
     versteht
    -0.08
     lançamento
    -0.08
    컴
    -0.08
    ента
    -0.08
     모바일
    -0.08
    ifi
    -0.08
     televis
    -0.08
     жар
    -0.08
    -tv
    -0.07
    POSITIVE LOGITS
     कप
    0.07
     suppose
    0.07
    uture
    0.07
     race
    0.07
     benefit
    0.07
     majority
    0.07
     especie
    0.07
     usher
    0.07
    range
    0.07
     multitude
    0.06
    Activations Density 0.001%

    No Known Activations