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. 130854
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -al
    -0.09
    .Timestamp
    -0.08
    @Id
    -0.08
    -major
    -0.08
    imestamp
    -0.07
    -on
    -0.07
    -variable
    -0.07
    INT
    -0.07
    .ADD
    -0.07
    Bounds
    -0.07
    POSITIVE LOGITS
     Rud
    0.09
     желательно
    0.09
     Sports
    0.09
     Cardi
    0.09
     Nav
    0.08
     Card
    0.08
     Chest
    0.08
     sports
    0.08
     Sama
    0.08
     кар
    0.08
    Activations Density 0.001%

    No Known Activations