© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12911
    Prev
    Next
    INDEX
    Explanations

    TaqMan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extraordinary
    -0.10
     scratched
    -0.09
     Thumb
    -0.09
     whatsoever
    -0.08
     arqu
    -0.08
    rometer
    -0.08
    rom
    -0.08
     roto
    -0.08
    Thumb
    -0.08
     avere
    -0.08
    POSITIVE LOGITS
    _EXP
    0.07
     compartment
    0.07
    ادي
    0.07
    .name
    0.07
    leggings
    0.07
    _GO
    0.07
    ewerk
    0.07
     �
    0.07
     Calend
    0.07
    lege
    0.07
    Activations Density 0.000%

    No Known Activations