© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8132
    Prev
    Next
    INDEX
    Explanations

    |

    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
     elbow
    -0.08
    ethyl
    -0.07
     PPE
    -0.07
    办
    -0.07
    apes
    -0.07
    .tk
    -0.07
     elbows
    -0.07
    aks
    -0.07
    oxide
    -0.07
    omelo
    -0.07
    POSITIVE LOGITS
     TBD
    0.09
     hingegen
    0.09
    AGR
    0.08
     hmm
    0.08
    ']:
    0.08
     org
    0.08
     mantel
    0.08
     schließlich
    0.08
     rst
    0.07
    opr
    0.07
    Activations Density 0.047%

    No Known Activations