© 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. 95051
    Prev
    Next
    INDEX
    Explanations

    javascript canvas code

    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
     grooming
    -0.09
    -0.08
     Thailand
    -0.08
     novel
    -0.08
     acabar
    -0.07
     τ
    -0.07
     tau
    -0.07
     fantasia
    -0.07
     eigen
    -0.07
     psoriasis
    -0.07
    POSITIVE LOGITS
    rgb
    0.09
     얻
    0.08
    fname
    0.08
     obtenido
    0.08
     slowed
    0.08
    _polygon
    0.08
    _cmd
    0.08
    stripe
    0.08
    二维
    0.07
    _shader
    0.07
    Activations Density 0.002%
    No Known Activations