© 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. 3-RESID-POST-AA
    11. 12751
    Prev
    Next
    INDEX
    Explanations

    uplifting

    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
     ta
    -0.09
     bitte
    -0.08
     mellitus
    -0.08
     ca
    -0.08
     billion
    -0.08
     bre
    -0.08
    .NULL
    -0.07
    Extreme
    -0.07
     разг
    -0.07
     पर्य
    -0.07
    POSITIVE LOGITS
    �
    0.08
     purposely
    0.08
    spiring
    0.07
     Didier
    0.07
     spelled
    0.07
     Babil
    0.07
     Grandpa
    0.07
     Press
    0.07
    _SP
    0.07
     verand
    0.07
    Activations Density 0.001%

    No Known Activations