Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11612
    Prev
    Next
    INDEX
    Explanations

    time intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bending
    -0.08
     mobilier
    -0.08
    统
    -0.08
     deficient
    -0.08
     løs
    -0.07
    olve
    -0.07
     Shoulder
    -0.07
     flour
    -0.07
     sfr
    -0.07
    visa
    -0.07
    POSITIVE LOGITS
    _INTERVAL
    0.16
    (interval
    0.15
    _interval
    0.15
    Interval
    0.15
     interval
    0.13
    .Interval
    0.13
    .interval
    0.13
     intervals
    0.13
    (minutes
    0.13
     intervalo
    0.12
    Activations Density 0.009%

    No Known Activations