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. 98209
    Prev
    Next
    INDEX
    Explanations

    den

    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
     dasar
    -0.09
    ology
    -0.09
    헤
    -0.08
    flight
    -0.07
     پاس
    -0.07
    heading
    -0.07
    lossen
    -0.07
    LOGY
    -0.07
    geven
    -0.07
     carrots
    -0.07
    POSITIVE LOGITS
    aturation
    0.13
    aturing
    0.13
    itr
    0.12
    it
    0.09
    atur
    0.09
    atuur
    0.09
    atures
    0.08
    itrag
    0.08
    ature
    0.08
    oise
    0.08
    Activations Density 0.001%

    No Known Activations