© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    English

    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
     solvents
    -0.08
    Customized
    -0.07
     artesanal
    -0.07
    收藏
    -0.07
     ẹ
    -0.07
    새
    -0.07
     solvent
    -0.07
     fulfilled
    -0.07
    _dr
    -0.07
    domin
    -0.07
    POSITIVE LOGITS
     moderna
    0.08
    .randrange
    0.08
    ankha
    0.08
     большая
    0.08
    ય
    0.08
    こんにちは
    0.08
     fejl
    0.08
     freeway
    0.07
    વે
    0.07
    aggia
    0.07
    Activations Density 0.004%

    No Known Activations