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. 58330
    Prev
    Next
    INDEX
    Explanations

    End

    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
    大厅
    -0.08
     tantal
    -0.08
     stanza
    -0.08
    डी
    -0.08
     delect
    -0.07
     naro
    -0.07
     idyll
    -0.07
     cinta
    -0.07
     lounge
    -0.07
    فاق
    -0.07
    POSITIVE LOGITS
     descendant
    0.08
     vermogen
    0.08
     בן
    0.08
    (MAX
    0.07
    ].[
    0.07
    folger
    0.07
     VBA
    0.07
     spreadsheets
    0.07
     ao
    0.07
     leeft
    0.07
    Activations Density 0.001%

    No Known Activations