© 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. 23-RESID-POST-AA
    11. 48629
    Prev
    Next
    INDEX
    Explanations

    Immaculate Conception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resources
    -0.09
     middelen
    -0.08
    ங
    -0.08
    ungle
    -0.08
    resources
    -0.08
    _resources
    -0.08
    资源
    -0.08
     hev
    -0.07
    ivne
    -0.07
    _one
    -0.07
    POSITIVE LOGITS
    ipation
    0.11
    uée
    0.08
    _DONE
    0.08
    .ss
    0.08
     DONE
    0.08
    ipada
    0.08
     sondern
    0.08
     pró
    0.08
    。不
    0.07
    olat
    0.07
    Activations Density 0.001%

    No Known Activations