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. 30779
    Prev
    Next
    INDEX
    Explanations

    Tech and education texts

    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
     Temos
    -0.08
    angalore
    -0.08
    (Rect
    -0.08
    assle
    -0.08
    .available
    -0.08
     abundant
    -0.07
    .Av
    -0.07
     Applicable
    -0.07
     sortes
    -0.07
    .subplots
    -0.07
    POSITIVE LOGITS
    /plain
    0.09
     GPT
    0.09
    encrypted
    0.08
     disguise
    0.08
     mensch
    0.08
     disguised
    0.08
     происх
    0.08
     blurry
    0.08
     принадлеж
    0.08
     Grammarly
    0.08
    Activations Density 0.006%

    No Known Activations