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. 109969
    Prev
    Next
    INDEX
    Explanations

    optimization problems

    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
    вания
    -0.08
    -0.08
    vation
    -0.07
    іння
    -0.07
    ಾವು
    -0.07
    verb
    -0.07
    ಾವಣೆ
    -0.07
     �
    -0.07
     towering
    -0.07
    lation
    -0.07
    POSITIVE LOGITS
     meet
    0.09
     satisfy
    0.08
    满足
    0.08
    Meet
    0.08
     configura
    0.08
     workable
    0.08
     tolerated
    0.08
    meet
    0.08
    _fit
    0.08
     Meet
    0.08
    Activations Density 0.027%

    No Known Activations