© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    Three

    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
     pedestal
    -0.08
    garan
    -0.08
    شا
    -0.08
     Lanz
    -0.08
     kendaraan
    -0.08
    zim
    -0.08
     lut
    -0.07
     Ren
    -0.07
     koriste
    -0.07
     Moss
    -0.07
    POSITIVE LOGITS
    rd
    0.11
    (三
    0.10
    'offre
    0.08
     child's
    0.08
     tern
    0.08
    -three
    0.08
    aktion
    0.08
     الثالث
    0.08
     الثلاث
    0.08
     triple
    0.07
    Activations Density 0.197%

    No Known Activations