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. 98088
    Prev
    Next
    INDEX
    Explanations

    bel

    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
    encio
    -0.08
    χω
    -0.08
    HER
    -0.08
    Steve
    -0.08
    änglich
    -0.08
     هد
    -0.07
    zonder
    -0.07
    Во
    -0.07
     أول
    -0.07
    ifiziert
    -0.07
    POSITIVE LOGITS
    ievably
    0.13
    ated
    0.12
    lezza
    0.11
    licos
    0.10
    ies
    0.10
    itt
    0.09
    uga
    0.09
    ied
    0.09
    lic
    0.09
    abor
    0.09
    Activations Density 0.002%

    No Known Activations