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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131023
    Prev
    Next
    INDEX
    Explanations

    ^

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inputs
    -0.08
    เห
    -0.08
    oust
    -0.07
    oth
    -0.07
    -0.07
    NT
    -0.07
    审
    -0.07
    ayu
    -0.07
     cleanliness
    -0.07
    ayela
    -0.07
    POSITIVE LOGITS
    _gp
    0.09
     കല
    0.09
     arranger
    0.08
    ങ്ങ
    0.08
     പങ്ക
    0.08
    gp
    0.08
    .fml
    0.08
    (logging
    0.08
    ങ്ങിയ
    0.07
     illustrates
    0.07
    Activations Density 0.000%

    No Known Activations