© 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. 11-RESID-POST-AA
    11. 108
    Prev
    Next
    INDEX
    Explanations

    Absence/nothingness

    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
     OK
    -0.08
    ड़क
    -0.08
     roundup
    -0.08
    koht
    -0.07
     desigual
    -0.07
    mr
    -0.07
     MR
    -0.07
     moderately
    -0.07
    िल
    -0.07
     indire
    -0.07
    POSITIVE LOGITS
     devoid
    0.12
     Null
    0.09
     ไม่มี
    0.09
    .Null
    0.09
    _null
    0.09
     શુ
    0.09
     Blank
    0.09
    	null
    0.09
    Null
    0.09
    .NULL
    0.09
    Activations Density 0.035%

    No Known Activations