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. 7-RESID-POST-AA
    6. 1959
    Prev
    Next
    INDEX
    Explanations

    II

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arp
    -0.08
    ା
    -0.08
    �
    -0.08
     clínicas
    -0.08
    ײַ
    -0.08
     Sai
    -0.08
    VECTOR
    -0.08
     nonsense
    -0.07
    ార్
    -0.07
     Biotechnology
    -0.07
    POSITIVE LOGITS
     fgets
    0.07
    -mid
    0.07
     play
    0.07
    करण
    0.07
    ociated
    0.07
    esseur
    0.07
     oyster
    0.07
     tab
    0.07
     multil
    0.06
     ಬಾರಿ
    0.06
    Activations Density 0.000%

    No Known Activations