© 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. 2523
    Prev
    Next
    INDEX
    Explanations

    gritty

    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
     mel
    -0.09
     Mel
    -0.08
    �
    -0.08
     Henry
    -0.08
     pun
    -0.08
     atu
    -0.08
     twin
    -0.08
     sis
    -0.08
     wrist
    -0.08
     Denn
    -0.08
    POSITIVE LOGITS
     gritty
    0.09
     bankruptcy
    0.08
     sit
    0.08
    noise
    0.07
     streets
    0.07
     animé
    0.07
    Noise
    0.07
     noise
    0.07
    housing
    0.07
     Calle
    0.07
    Activations Density 0.002%

    No Known Activations