Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2234
    Prev
    Next
    INDEX
    Explanations

    quel

    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
    iav
    -0.08
    ї
    -0.08
     taxable
    -0.08
     VLAN
    -0.07
    (D
    -0.07
     લી
    -0.07
    anaan
    -0.07
    byter
    -0.07
     VAR
    -0.07
    (express
    -0.07
    POSITIVE LOGITS
     Förder
    0.09
     çalış
    0.08
     kin
    0.08
    _modes
    0.07
     boosters
    0.07
    ർ
    0.07
     Kens
    0.07
    ực
    0.07
     πι
    0.07
     तू
    0.07
    Activations Density 0.000%

    No Known Activations