© 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. 1334
    Prev
    Next
    INDEX
    Explanations

    确定

    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
     deber
    -0.07
     grav
    -0.07
     engulf
    -0.07
     attr
    -0.07
     अह
    -0.07
    .work
    -0.07
     Ae
    -0.07
     مث
    -0.07
    று
    -0.07
     Tc
    -0.06
    POSITIVE LOGITS
    Oc
    0.08
     germs
    0.08
     scalp
    0.08
     Gala
    0.08
     eas
    0.08
     Thom
    0.08
     değ
    0.08
    Ink
    0.08
     Oc
    0.07
     Holmes
    0.07
    Activations Density 0.001%

    No Known Activations