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. 98413
    Prev
    Next
    INDEX
    Explanations

    ipl

    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
     produjo
    -0.09
     cis
    -0.08
     সৈ
    -0.08
     Cis
    -0.07
    cis
    -0.07
    afen
    -0.07
    ίκ
    -0.07
    ാട്ട
    -0.07
     sufrió
    -0.07
    >x
    -0.07
    POSITIVE LOGITS
    ined
    0.13
    inaire
    0.10
    anity
    0.09
    ines
    0.08
    101
    0.08
    inal
    0.08
     Ari
    0.08
    озна
    0.07
     ビ
    0.07
    omatic
    0.07
    Activations Density 0.000%

    No Known Activations