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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58451
    Prev
    Next
    INDEX
    Explanations

    }

    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
    获得
    -0.08
     gu
    -0.08
     boos
    -0.08
     fashionable
    -0.08
    (er
    -0.07
     simultaneous
    -0.07
     coupled
    -0.07
     metaphor
    -0.07
     rip
    -0.07
     kontin
    -0.07
    POSITIVE LOGITS
    আমি
    0.08
    I've
    0.08
    xm
    0.08
    mons
    0.07
    Bone
    0.07
     Quite
    0.07
    Quite
    0.07
    iteri
    0.07
     I've
    0.07
    _der
    0.07
    Activations Density 0.029%

    No Known Activations