© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    stick

    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
    -0.08
    (ord
    -0.08
     سرو
    -0.07
    ඳ
    -0.07
     sofa
    -0.07
    _COUNTER
    -0.07
     panna
    -0.07
     quantify
    -0.07
     تیار
    -0.07
     Frag
    -0.07
    POSITIVE LOGITS
     sem
    0.08
     overlapping
    0.08
     rebellion
    0.08
     crystalline
    0.08
     Revel
    0.07
    connecting
    0.07
    ees
    0.07
     krist
    0.07
     Kip
    0.07
    appe
    0.07
    Activations Density 0.002%
    No Known Activations