© 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. 68058
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     vandal
    -0.09
    nos
    -0.08
     आर
    -0.07
    dr
    -0.07
    _tem
    -0.07
    iones
    -0.07
     chlor
    -0.07
    awang
    -0.07
     amb
    -0.07
    bold
    -0.07
    POSITIVE LOGITS
    Anyway
    0.10
     unclear
    0.08
     dependiendo
    0.08
     depending
    0.08
    ම්
    0.08
    Sar
    0.08
     Anyway
    0.08
    halo
    0.07
    Like
    0.07
    涙
    0.07
    Activations Density 0.170%

    No Known Activations