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. 90076
    Prev
    Next
    INDEX
    Explanations

    common

    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
    yes
    -0.09
    Yes
    -0.09
     yes
    -0.08
     coded
    -0.08
    Everything
    -0.08
    structured
    -0.07
     -*-
    -0.07
    Dims
    -0.07
     misuse
    -0.07
    Structured
    -0.07
    POSITIVE LOGITS
     externa
    0.10
     lijnen
    0.09
     exterior
    0.09
     unob
    0.08
     الخارجية
    0.08
     mantel
    0.08
     Exterior
    0.08
     externo
    0.08
     પટ
    0.08
     fina
    0.08
    Activations Density 0.005%

    No Known Activations