© 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. 7-RESID-POST-AA
    11. 1262
    Prev
    Next
    INDEX
    Explanations

    Reading prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bekannt
    -0.08
     curb
    -0.07
    �
    -0.07
     antis
    -0.07
     Concert
    -0.07
     tracking
    -0.07
    113
    -0.07
     audio
    -0.07
     regrett
    -0.07
     shots
    -0.06
    POSITIVE LOGITS
    章
    0.11
     aloud
    0.11
     Arth
    0.10
     banyere
    0.09
     кай
    0.09
     внимательно
    0.09
    _signup
    0.09
     atent
    0.08
    .Reader
    0.08
     nook
    0.08
    Activations Density 0.086%

    No Known Activations