Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102948
    Prev
    Next
    INDEX
    Explanations

    accessibility

    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
     oil
    -0.09
    _coeff
    -0.08
     druk
    -0.08
     satisfactory
    -0.08
    _SERV
    -0.08
    -0.08
     oily
    -0.08
     majority
    -0.08
     rash
    -0.08
     levert
    -0.08
    POSITIVE LOGITS
     aria
    0.10
    -labelledby
    0.09
     {!!
    0.08
     Rachel
    0.08
     escond
    0.08
     helpers
    0.08
    ल्या
    0.08
     ಟ
    0.07
     Weiter
    0.07
     Palacio
    0.07
    Activations Density 0.003%

    No Known Activations