© 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. 11-RESID-POST-AA
    11. 129434
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rench
    -0.08
     Entwicklungen
    -0.07
    .dir
    -0.07
    ರ್ಜ
    -0.07
     Partie
    -0.07
     Tunnel
    -0.07
     Soms
    -0.07
     Stable
    -0.07
     되어
    -0.07
     관계
    -0.07
    POSITIVE LOGITS
     blister
    0.08
    bl
    0.08
     prohibits
    0.08
     scall
    0.08
     straf
    0.08
     forbid
    0.08
     bl
    0.07
     prohibit
    0.07
    unwrap
    0.07
    שט
    0.07
    Activations Density 0.007%

    No Known Activations