Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49364
    Prev
    Next
    INDEX
    Explanations

    essential

    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
    �
    -0.08
     수도
    -0.08
     कृ
    -0.07
     satisfe
    -0.07
    overs
    -0.07
    준
    -0.07
    meer
    -0.07
    Turning
    -0.07
    liku
    -0.07
     தய
    -0.07
    POSITIVE LOGITS
     oils
    0.09
     herbs
    0.09
     herbal
    0.09
     npm
    0.08
    .compose
    0.08
     glycer
    0.08
     composing
    0.08
     tint
    0.08
     dyes
    0.08
     brass
    0.08
    Activations Density 0.002%

    No Known Activations