© 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. 65439
    Prev
    Next
    INDEX
    Explanations

    AG

    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
     TO
    -0.08
     covering
    -0.07
     Zurich
    -0.07
     exchanges
    -0.07
     GIR
    -0.07
     POINTER
    -0.07
     PIC
    -0.07
     deterministic
    -0.06
     Eur
    -0.06
     ENT
    -0.06
    POSITIVE LOGITS
     ideals
    0.09
    Баш
    0.09
     ideaal
    0.09
     Ide
    0.08
    ideal
    0.08
    anya
    0.08
    bull
    0.08
     аты
    0.08
    45
    0.08
     많
    0.08
    Activations Density 0.000%

    No Known Activations