© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47988
    Prev
    Next
    INDEX
    Explanations

    Objective-C code

    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
     Debian
    -0.11
     Windows
    -0.09
     Linux
    -0.09
     Ubuntu
    -0.09
    linux
    -0.09
     Lenovo
    -0.09
    _windows
    -0.08
    _bins
    -0.08
    tpl
    -0.08
     Asus
    -0.08
    POSITIVE LOGITS
     NSString
    0.34
     NSLog
    0.33
    NSString
    0.32
     NSDictionary
    0.30
     CGFloat
    0.30
     NSMutable
    0.30
     NSURL
    0.30
     NSDate
    0.30
     XCTAssert
    0.30
     NSLocalized
    0.30
    Activations Density 0.025%

    No Known Activations