© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1259
    Prev
    Next
    INDEX
    Explanations

    bear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
     יה
    -0.08
    �
    -0.08
    antis
    -0.08
     antis
    -0.08
     esm
    -0.07
     ves
    -0.07
     aneur
    -0.07
     explosive
    -0.07
     см
    -0.07
    POSITIVE LOGITS
     тр
    0.09
     dut
    0.08
     Cruc
    0.08
     incl
    0.07
     ב
    0.07
     thresh
    0.07
     Rede
    0.07
     wenn
    0.07
    �
    0.07
     thorough
    0.07
    Activations Density 0.004%

    No Known Activations