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. 130959
    Prev
    Next
    INDEX
    Explanations

    call and response/technical structures

    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
    어서
    -0.08
    fsi
    -0.08
    ertas
    -0.08
    лиж
    -0.07
     serais
    -0.07
     aja
    -0.07
     सें
    -0.07
    руз
    -0.07
     verbringen
    -0.07
     because
    -0.07
    POSITIVE LOGITS
    -no
    0.11
     No
    0.10
    -No
    0.10
     melodic
    0.09
    -navigation
    0.09
    -mus
    0.09
    .No
    0.08
     Navigation
    0.08
    _NO
    0.08
    -elect
    0.08
    Activations Density 0.000%

    No Known Activations