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. 43684
    Prev
    Next
    INDEX
    Explanations

    Backing up data

    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
     growth
    -0.08
    INF
    -0.07
    ρέπει
    -0.07
     gaze
    -0.07
    imbra
    -0.07
    Growth
    -0.07
    inf
    -0.07
    Inf
    -0.07
    ळ
    -0.07
    .coin
    -0.07
    POSITIVE LOGITS
     precaution
    0.11
     previo
    0.10
     beforehand
    0.10
     консульта
    0.10
     voordat
    0.09
     préalable
    0.09
     cautious
    0.09
     kafin
    0.09
     Backup
    0.09
     सलाह
    0.09
    Activations Density 0.006%

    No Known Activations