© 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. 6177
    Prev
    Next
    INDEX
    Explanations

    p

    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
     ráp
    -0.09
     rep
    -0.08
     Raid
    -0.08
    (rep
    -0.08
    (proto
    -0.08
     poor
    -0.08
    'ap
    -0.08
     ап
    -0.08
    "path
    -0.08
    	path
    -0.08
    POSITIVE LOGITS
     PRES
    0.16
    _pres
    0.15
    -pres
    0.15
    Pres
    0.14
    pres
    0.13
     presidente
    0.13
     presid
    0.13
     Pres
    0.13
     pres
    0.13
     anonym
    0.13
    Activations Density 0.001%

    No Known Activations