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. 97123
    Prev
    Next
    INDEX
    Explanations

    b

    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
     omitted
    -0.09
     Local
    -0.08
    мож
    -0.08
     Export
    -0.07
     �
    -0.07
    -0.07
     simple
    -0.07
     cruises
    -0.07
     Output
    -0.07
     Recovery
    -0.07
    POSITIVE LOGITS
    (cliente
    0.09
     알
    0.08
     AV
    0.08
    _b
    0.08
    [F
    0.08
     andando
    0.08
     impur
    0.07
     ister
    0.07
     Fernando
    0.07
    futa
    0.07
    Activations Density 0.000%

    No Known Activations