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. 101790
    Prev
    Next
    INDEX
    Explanations

    aesthetics

    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
    packed
    -0.07
    voldoende
    -0.07
    meld
    -0.07
    exports
    -0.07
    ';↵↵
    -0.07
    oor
    -0.07
    (export
    -0.07
    ậm
    -0.07
    EXPORT
    -0.07
    oring
    -0.07
    POSITIVE LOGITS
     holdem
    0.08
     lwjgl
    0.08
     escuchar
    0.08
     Pleasure
    0.08
     będ
    0.08
     Lowell
    0.08
     luister
    0.08
     ŵ
    0.07
    举行
    0.07
     Adm
    0.07
    Activations Density 0.001%

    No Known Activations